Engineer

University of North Carolina at Chapel Hill•Chapel Hill, NC

77d

About The Position

We are looking for individuals with a strong theoretical and practical background in large language models, machine learning, and natural language processing, combined with a collaborative spirit and a drive for problem-solving. You'll join a multidisciplinary team that values diversity and brings together expertise in software engineering, big data, clinical informatics, and medicine.

Requirements

Bachelor's degree in Computer Science, Electrical Engineering, or related fields.
Expertise in Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), deep learning frameworks.
Proficiency in Python and frameworks such as PyTorch, TensorFlow, Hugging Face Transformers, or LangChain
Familiarity with clinical or healthcare data (e.g., EHRs, clinical notes, structured claims data)
Proven research record with peer-reviewed publications in relevant fields
Strong problem-solving skills and the ability to work in a collaborative environment.

Nice To Haves

Distributed parallel training and parameter-efficient tuning.
Familiarity with multi-modal foundation models, HITL techniques, and prompt engineering.
Experience with LLM fine-tuning, prompt engineering, or retrieval-augmented generation (RAG)
Experience deploying large-scale machine learning models in cloud environments.

Responsibilities

Design, fine-tune, and evaluate large language models (LLMs) tailored to domain-specific applications using techniques such as transfer learning, LoRA, and reinforcement learning with human feedback (RLHF).
Build intelligent applications powered by LLMs, including chatbots, virtual agents, clinical decision tools, or document analyzers, using frameworks like LangChain, LlamaIndex, or semantic search pipelines.
Develop scalable LLM pipelines and infrastructure, including data ingestion, preprocessing, model serving (via GPU/TPU), and continuous performance monitoring.
Integrate commercial and open-source LLMs (e.g., OpenAI GPT, Claude, Mistral, LLaMA) via APIs or local deployment into digital health or enterprise systems.
Craft and iterate prompts using advanced prompt engineering and chain-of-thought strategies to improve output relevance, tone, factuality, and task completion.
Implement retrieval-augmented generation (RAG) architectures to enhance context awareness using vector databases (e.g., Pinecone, FAISS, Weaviate).
Evaluate LLM performance using automated and human-in-the-loop methods to assess accuracy, hallucination, safety, and user satisfaction.
Collaborate across disciplines with data scientists, UX designers, domain experts, and MLOps to ensure usability, performance, and alignment with real-world needs.
Monitor and optimize system performance, including latency, throughput, token usage, and model cost-effectiveness across deployment environments.
Stay current with advancements in generative AI, contributing to the internal knowledge base and driving adoption of best practices for ethical and responsible LLM use.

Benefits

University employees can choose from a wide range of professional training opportunities for career growth, skill development and lifelong learning and enjoy exclusive perks that include numerous retail and restaurant discounts, savings on local child care centers and special rates for performing arts events.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume